|
|
@19778
|
16 years |
vboxsync |
Fixed the stale TLB detection
|
|
|
@19777
|
16 years |
vboxsync |
Atomic write
|
|
|
@19776
|
16 years |
vboxsync |
Reapplied fixed 47403
|
|
|
@19775
|
16 years |
vboxsync |
Reapplied 47403
|
|
|
@19773
|
16 years |
vboxsync |
Fixed accidental commits
|
|
|
@19772
|
16 years |
vboxsync |
Backed out 47401-3 for now
|
|
|
@19771
|
16 years |
vboxsync |
More atomic writes
|
|
|
@19770
|
16 years |
vboxsync |
Missing unlocks in error cases
|
|
|
@19769
|
16 years |
vboxsync |
Deal with stale TLB entries for harmless page entry updates.
Wider locking.
|
|
|
@19765
|
16 years |
vboxsync |
Atomically update page table/directory entries.
|
|
|
@19753
|
16 years |
vboxsync |
More stats.
|
|
|
@19752
|
16 years |
vboxsync |
TM: Revised tmVirtualSyncGetEx for SMP.
|
|
|
@19747
|
16 years |
vboxsync |
TM: Cleaned up pausing and resuming the clocks.
|
|
|
@19740
|
16 years |
vboxsync |
PDMAllCritSect.cpp: Use ASMAtomicWriteHandle.
|
|
|
@19725
|
16 years |
vboxsync |
Logging update
|
|
|
@19721
|
16 years |
vboxsync |
Locking assertions
|
|
|
@19720
|
16 years |
vboxsync |
Use an ordered update
|
|
|
@19709
|
16 years |
vboxsync |
TM,EM: More TM/SMP work, still stuff in progress.
|
|
|
@19693
|
16 years |
vboxsync |
Emulate the mwait instruction with VT-x and AMD-V as well.
|
|
|
@19691
|
16 years |
vboxsync |
SyncPT must be protected by a lock.
|
|
|
@19690
|
16 years |
vboxsync |
More pgm pool locking.
|
|
|
@19682
|
16 years |
vboxsync |
Try to cleanup after one VCPU goes into guru meditation mode. Release …
|
|
|
@19680
|
16 years |
vboxsync |
More locking
|
|
|
@19677
|
16 years |
vboxsync |
Wrong assertions
|
|
|
@19676
|
16 years |
vboxsync |
More verbose assertions
|
|
|
@19675
|
16 years |
vboxsync |
Must acquire the pgm lock in pgm pool access handlers too.
|
|
|
@19674
|
16 years |
vboxsync |
Use the pgm lock during pgmPoolAlloc.
|
|
|
@19667
|
16 years |
vboxsync |
Cleaned up
|
|
|
@19666
|
16 years |
vboxsync |
Deal with VMMCALLHOST_MMHYPER_LOCK correctly.
|
|
|
@19663
|
16 years |
vboxsync |
Protect the MM hypervisor heap with a critical section.
|
|
|
@19660
|
16 years |
vboxsync |
TM+affected: SMP changes in progress.
|
|
|
@19628
|
16 years |
vboxsync |
Lock counter instead of a lock flag.
|
|
|
@19627
|
16 years |
vboxsync |
PGM pool: allow multiple users of top-level paging structures …
|
|
|
@19611
|
16 years |
vboxsync |
Change the EM state to EMSTATE_HALTED after receiving the startup IPI.
|
|
|
@19597
|
16 years |
vboxsync |
PDMCritSectIsOwner fix
|
|
|
@19596
|
16 years |
vboxsync |
PDMCritSectIsOwner: pretend critical sections scheduled for release …
|
|
|
@19593
|
16 years |
vboxsync |
Split up PDM.
|
|
|
@19590
|
16 years |
vboxsync |
Added PDMCritSectGetRecursion
|
|
|
@19586
|
16 years |
vboxsync |
Missing pgmUnlock
|
|
|
@19572
|
16 years |
vboxsync |
Started with ring 0 stack trace dump support.
|
|
|
@19538
|
16 years |
vboxsync |
TM: Moved TMR3TimerDestroy from TMAll.cpp to TM.cpp.
|
|
|
@19537
|
16 years |
vboxsync |
TMR3TimerDestroy: rewrite to ring-3 only.
|
|
|
@19516
|
16 years |
vboxsync |
Always call pgmPoolSyncCR3 from PGMSyncCR3 (regardless of guest paging …
|
|
|
@19507
|
16 years |
vboxsync |
TM: TMTimerDestroy -> TMR3TimerDestroy. (trying to simplify)
|
|
|
@19503
|
16 years |
vboxsync |
Fixed r47022 regression
|
|
|
@19502
|
16 years |
vboxsync |
TMAll.cpp: removed two assertions in TMTimerStop as well.
|
|
|
@19500
|
16 years |
vboxsync |
TM: Moved the WarpDrive feature out of TMVirtual and made the setter …
|
|
|
@19498
|
16 years |
vboxsync |
TMAll.cpp: Drop two wrong assertions in TMTimerSet (the queue might be …
|
|
|
@19492
|
16 years |
vboxsync |
TMAll: Fixed assertion in tmTimerQueueSanityChecks.
|
|
|
@19488
|
16 years |
vboxsync |
Made pgmPoolSyncCR3 a bit more SMP safe (pgmPoolClearAll still to be done).
|
|
|
@19487
|
16 years |
vboxsync |
Adjusted assertion for now
|
|
|
@19486
|
16 years |
vboxsync |
TM: Added lock stubbing for debugging purposes (disabled).
|
|
|
@19480
|
16 years |
vboxsync |
Release the PGM lock when calling physical handlers …
|
|
|
@19479
|
16 years |
vboxsync |
Got rid of obsolete assertion
|
|
|
@19476
|
16 years |
vboxsync |
Moved VMMR3SendInitIpi/Sipi
|
|
|
@19475
|
16 years |
vboxsync |
VMM: sending init IPI
|
|
|
@19474
|
16 years |
vboxsync |
MMIO locking
|
|
|
@19472
|
16 years |
vboxsync |
Protect port I/O with a critical section.
|
|
|
@19471
|
16 years |
vboxsync |
Added PGMIsLocked & PDMCritSectIsLocked
|
|
|
@19468
|
16 years |
vboxsync |
VMM: better SIPI sending, reschedule to R3 as needed
|
|
|
@19450
|
16 years |
vboxsync |
VMMAll: updated SIPI sketch.
|
|
|
@19445
|
16 years |
vboxsync |
VMMAll.cpp: How to wake up a CPU (on SIPI), heed todos.
|
|
|
@19444
|
16 years |
vboxsync |
TM: Serialize EMT access using a critsect.
|
|
|
@19439
|
16 years |
vboxsync |
PDM: Renamed PDMR3CritSectTryEnter to PDMCritSectTryEnter.
|
|
|
@19437
|
16 years |
vboxsync |
SMP: send SIPI notification from APIC, let VM handle what really do
|
|
|
@19434
|
16 years |
vboxsync |
Further splitup of VMM (ring 0 jump buffer).
|
|
|
@19415
|
16 years |
vboxsync |
Corrected assertions
|
|
|
@19400
|
16 years |
vboxsync |
VM: VMR3Notify*FF refactorying (for poking); converting fNotifiedREM …
|
|
|
@19395
|
16 years |
vboxsync |
GVMM,VM: Register the other EMTs or we assert painfully in …
|
|
|
@19358
|
16 years |
vboxsync |
Fixed infinite recursion in VMMGetCpu (ring 0).
|
|
|
@19334
|
16 years |
vboxsync |
DBGF,SELM,DBGC,++: Refactored the selector info querying and usage, …
|
|
|
@19330
|
16 years |
vboxsync |
Cleaned up a bit
|
|
|
@19329
|
16 years |
vboxsync |
Removed pgmPoolGetPageByHCPhys.
|
|
|
@19324
|
16 years |
vboxsync |
fVirtualTicking -> cVirtualTicking. Turn on the virtual timer only …
|
|
|
@19319
|
16 years |
vboxsync |
More verbose assertion
|
|
|
@19300
|
16 years |
vboxsync |
VMReq,*: Replaced VMREQDEST with VMCPUID because it's a pain to have …
|
|
|
@19293
|
16 years |
vboxsync |
DBGF,VMM: SMP refactoring of the DBGF disassembler code. Changed …
|
|
|
@19286
|
16 years |
vboxsync |
VMM,VBoxDbg: SMP refactoring, part 1.
|
|
|
@19263
|
16 years |
vboxsync |
Got rid of more SMP related assertions
|
|
|
@19262
|
16 years |
vboxsync |
Introduced PDMCritSectIsOwnerEx.
|
|
|
@19260
|
16 years |
vboxsync |
Backed out PDMCritSectIsOwner change
|
|
|
@19259
|
16 years |
vboxsync |
Fixes for guest smp assertions
|
|
|
@19246
|
16 years |
vboxsync |
Fixed regression from r46484.
|
|
|
@19240
|
16 years |
vboxsync |
SMP guest fixes
|
|
|
@19232
|
16 years |
vboxsync |
Assertions for raw mode & SMP guests.
|
|
|
@19228
|
16 years |
vboxsync |
Shortcut for one CPU
|
|
|
@19227
|
16 years |
vboxsync |
Implemented VMMGetCpu in ring 0. (SMP guests)
|
|
|
@19217
|
16 years |
vboxsync |
UVM splitup for SMP guests. Global and local request packets supported.
|
|
|
@19195
|
16 years |
vboxsync |
Fixed possible corruption due to RC cache entry reuse.
|
|
|
@19180
|
16 years |
vboxsync |
PGMAllPhys.cpp: PGMPhysGCPhys2HCPhys should take the pgm lock before …
|
|
|
@19175
|
16 years |
vboxsync |
Paranoia
|
|
|
@19141
|
16 years |
vboxsync |
Action flags breakup.
Fixed PGM saved state loading of 2.2.2 images. …
|
|
|
@19092
|
16 years |
vboxsync |
PGMAllPhys.cpp: Fixed wrong (logrel) assertion.
|
|
|
@19076
|
16 years |
vboxsync |
CPUMGetGuestCpuId needs a pVCpu parameter.
|
|
|
@19075
|
16 years |
vboxsync |
CPUMGetGuestCpuIdStdRCPtr -> R3
|
|
|
@19032
|
16 years |
vboxsync |
Split TM for SMP guests.
|
|
|
@19024
|
16 years |
vboxsync |
PGM: Moved shadow mode exit and re-enter from PGMAllPool.cpp to …
|
|
|
@19015
|
16 years |
vboxsync |
Split up TRPM. (guest SMP)
|
|
|
@18992
|
16 years |
vboxsync |
More PGM api changes
|
|
|
@18988
|
16 years |
vboxsync |
PGM api changes
|
|
|